公开(公告)号：US20220237513A1

公开(公告)日：2022-07-28

申请号：US17587291

申请日：2022-01-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wenlong HE ,  Ihor VASYLTSOV ,  Gang SUN ,  Duanhui LIU

IPC: G06N20/00 ,  G06N7/00 ,  G06K9/62

Abstract: A method with quantization for a deep learning model includes: determining a second model by quantizing a first model based on a quantization parameter; determining a real value of multi optimization target parameter by testing the second model; calculating a loss function based on the real value of the multi optimization target parameter, an expected value of the multi optimization target parameter, and a constraint value of the multi optimization target parameter; updating the quantization parameter based on the loss function and using the second model as the first model; iteratively executing the foregoing operations until a preset condition is satisfied; and in response to the preset condition being satisfied, determining an optimal quantization parameter and using, as a final quantization model, the first model that executes quantization based on the optimal quantization parameter.

公开(公告)号：US20240062049A1

公开(公告)日：2024-02-22

申请号：US18355619

申请日：2023-07-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yujie ZENG ,  Wenlong HE ,  Lin CHEN ,  Ihor VASYLTSOV

IPC: G06N3/047 ,  G06N3/08

CPC classification number: G06N3/047 ,  G06N3/08

Abstract: A processor implemented method including iteratively training a model through repeated training operations, including calculating a respective sensitivity of each layer of plural layers included in the model, the model including a machine-learning model, calculating a first maintenance probability for a t-th repeated training of the model, calculating a respective maintenance probability of each of the plural layers of the model based on the respective sensitivity of each of the plural layers and based on the first maintenance probability for the t-th repeated training of the model, and performing the t-th repeated training of the model including training selected one or more maintenance layers, of the plural layers of the model, whose respective maintenance probabilities satisfy a first predetermined maintenance condition.